Due to the advantages of Synthetic Aperture Radar (SAR), the study of Automatic Target Recognition (ATR) has become a hot topic. Deep learning, especially in the case of a Convolutional Neural Network (CNN), works in an end-to-end way and has powerful feature-extracting abilities. Thus, researchers in SAR ATR also seek solutions from deep learning. We review the related algorithms with regard to SAR ATR in this paper. We firstly introduce the commonly used datasets and the evaluation metrics. Then, we introduce the algorithms before deep learning. They are template-matching-, machine-learning- and model-based methods. After that, we introduce mainly the SAR ATR methods in the deep-learning era (after 2017); those methods are the core of the paper. The non-CNNs and CNNs, that is, those used in SAR ATR, are summarized at the beginning. We found that researchers tend to design specialized CNN for SAR ATR. Then, the methods to solve the problem raised by limited samples are reviewed. They are data augmentation, Generative Adversarial Networks (GAN), electromagnetic simulation, transfer learning, few-shot learning, semi-supervised learning, metric leaning and domain knowledge. After that, the imbalance problem, real-time recognition, polarimetric SAR, complex data and adversarial attack are also reviewed. The principles and problems of them are also introduced. Finally, the future directions are conducted. In this part, we point out that the dataset, CNN architecture designing, knowledge-driven, real-time recognition, explainable and adversarial attack should be considered in the future. This paper gives readers a quick overview of the current state of the field.

Deep learning-based object detectors have demonstrated remarkable performance in recent years, including their application in Synthetic Aperture Radar (SAR) ship detection. However, these detectors often adopt backbones borrowed from classification models, requiring pre-training as a preliminary step. In addition, these borrowed backbones have several limitations that hinder their effectiveness when applied to SAR images. To overcome these drawbacks and improve accuracy, we designed a lightweight backbone called SAR ship detection backbone and an attention frontend network called SAR ship detection frontend to train ship detectors from scratch. The former is a meticulously designed backbone that leverages techniques such as cross-spatial partial dense blocks to extract features and has improved efficiency in accurately locating small ships. The latter is a carefully designed frontend network equipped with an attention module for prediction. The attention module comprises a spatial attention path, channel attention path and identity mapping path. It facilitates the network's learning of more meaningful spatially and channel-wise features. In addition, we defined the scales and aspect ratios of bounding boxes in datasets. The one2one label assigning strategy was used to match every anchor box with the corresponding ground truth. Complete intersection over union loss was also used to improve the performance of regression. The results obtained from public datasets show a favorable tradeoff between accuracy and time consumption. We also found that the detectors trained from scratch relied on the volume of the training dataset. The findings of this work can be used as a reference for researchers to design SAR ship detectors tailored to their specific requirements and demands.

Aeromagnetic surveys are widely used in geological exploration, mineral resource assessment, environmental monitoring, military reconnaissance, and other areas. It is necessary to perform magnetic compensation for interference in these fields. In recent years, large unmanned aerial vehicles (UAVs) have been more suitable for magnetic detection missions because of the greater loads they can carry. This article proposes some methods for the magnetic compensation of large multiload UAVs. Because of the interference of the large platform and instrument noise, the standard deviations (stds) of the compensation data used in this paper are larger. At the beginning of this article, using the traditional T-L model, we avoid the shortcomings of the anti-magnetic interference ability of triaxial magnetic gate magnetometers. The direction cosine information is obtained by using an inertial navigation system, the global positioning system, and a triaxial magnetic gate magnetometer. Then, we increase the amplitude of the maneuvers in the compensation process; this reduces the multicollinearity problems in the compensation matrix to a certain extent, but it also results in greater magnetic field interference. Lastly, we employ the method of Lasso regularization Newton iteration (LRNM). Compared to the traditional methods of least squares (LS) and singular value decomposition (SVD), LRNM provides improvements of 34% and 27%, respectively. In summary, this series of schemes can be used to perform effective compensation for large multi-load UAVs and improve the actual use of large UAVs, making them more accurate in the measurement of aeromagnetic survey data.

Although advanced deep learning techniques have significantly improved SAR ship detection, accurately detecting small ships remains challenging due to their limited size and the few appearance and geometric clues available. In order to solve this problem, we propose several small object detection strategies. The backbone network uses space-to-depth convolution to replace stride and pooling. It reduces information loss during down-sampling. The neck integrates multiple layers of features globally and injects global and local information into different levels. It avoids the inherent information loss of traditional feature pyramid networks and strengthens the information fusion ability without significantly increasing latency. The proposed intersection-of-union considers the center distance and scale of small ships specifically. It reduces the sensitivity of intersection-of-union to positional deviations of small ships, which is helpful for training toward small ships. During training, the smaller the localization loss of small ships, the greater their localization loss gains are. By this, the supervision of small ships is strengthened in the loss function, which can make the losses more biased toward small ships. A series of experiments are conducted on two commonly used datasets, SSDD and SAR-Ship-Dataset. The experimental results show that the proposed method can detect small ships successfully and thus improve the overall performance of detectors.

The deep learning models used in SAR ship detection always have a large model size and are computation intensive, which hinders the applications in real-time scene. In this paper, we aim to solve this problem by the whole process collaborative designing. The whole process incorporates the backbone, neck, head, label assignment and loss function. They are improved and optimized to best balance the accuracy and latency of the detector. The backbone, neck and head are improved for fusing features better according to the special characteristics of SAR images so as to increase the accuracy and reduce the latency. The anchor, label assignment and loss function are improved for utilizing samples better according to the characteristics of sparse distribution of ships so as to increase the accuracy. The proposed method achieved 97.6%, 91.2%, 91.2% and 93.6% AP50 with 108 FPS on SSDD, SAR-Ship-Dataset, AIR-SARShip and HRSID respectively. It shows great superiority in accuracy and latency compare with the other advanced detectors. This study shows that the proposed whole process collaborative designing can realize real-time SAR ship detection compare with the individual innovation. The future researchers can design the lightweight according to their demand based on the findings in this paper.

According to the limitations of single channel Frequency Modulation Continuous Wave (FMCW) Synthetic Aperture Radar (SAR), Digital Beamforming (DBF) technology is introduced to improve system performance. Combined with multiple receive apertures, DBF FMCW SAR can obtain high resolution in low pulse repetition frequency, which can increase the processing gain and decrease the sampling frequency. The received signal model of DBF FMCW SAR is derived. The continuous antenna motion which is the main characteristic of FMCW SAR received signal is taken into account in the whole signal processing. The detailed imaging diagram of DBF FMCW SAR is given. A reference system is also demonstrated in the paper by comparing with a single channel FMCW SAR. The validity of the presented diagram is demonstrated with a point target simulation results.